diff --git a/api/mlApi/download.py b/api/mlApi/data_preprocess.py
similarity index 100%
rename from api/mlApi/download.py
rename to api/mlApi/data_preprocess.py
diff --git a/api/mlApi/termsMlModel.py b/api/mlApi/termsMlModel.py
deleted file mode 100644
index bd98839..0000000
--- a/api/mlApi/termsMlModel.py
+++ /dev/null
@@ -1,74 +0,0 @@
-import torch
-from torch.utils.data import DataLoader, Dataset
-from transformers import BertTokenizer, BertForSequenceClassification, AdamW, get_linear_schedule_with_warmup
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score
-
-def load_dataset(dataset_path):
-    # Replace this with your actual dataset loading code
-    import pandas as pd
-    df = pd.read_csv(dataset_path)
-    texts = df['text'].tolist()
-    labels = df['label'].tolist()
-    return texts, labels
-
-def preprocess_data(texts, labels, max_length):
-    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-    encodings = tokenizer(texts, truncation=True, padding='max_length', max_length=max_length, return_tensors='pt')
-    dataset = DarkPatternDataset(encodings['input_ids'], encodings['attention_mask'], torch.tensor(labels))
-    return dataset
-
-def train_model(model, train_dataloader, val_dataloader, epochs, learning_rate):
-    optimizer = AdamW(model.parameters(), lr=learning_rate)
-    total_steps = len(train_dataloader) * epochs
-    scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=0, num_training_steps=total_steps)
-
-    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-    model.to(device)
-    model.train()
-
-    for epoch in range(epochs):
-        for batch in train_dataloader:
-            input_ids = batch['input_ids'].to(device)
-            attention_mask = batch['attention_mask'].to(device)
-            labels = batch['labels'].to(device)
-
-            optimizer.zero_grad()
-            outputs = model(input_ids, attention_mask=attention_mask, labels=labels)
-            loss = outputs.loss
-            loss.backward()
-            optimizer.step()
-            scheduler.step()
-
-def evaluate_model(model, val_dataloader, device='cpu'):
-    model.eval()
-    val_predictions = []
-    val_true_labels = []
-
-    with torch.no_grad():
-        for batch in val_dataloader:
-            input_ids = batch['input_ids'].to(device)
-            attention_mask = batch['attention_mask'].to(device)
-            labels = batch['labels'].to(device)
-
-            outputs = model(input_ids, attention_mask=attention_mask)
-            logits = outputs.logits
-            predictions = torch.argmax(logits, dim=1).cpu().numpy()
-
-            val_predictions.extend(predictions)
-            val_true_labels.extend(labels.cpu().numpy())
-
-    accuracy = accuracy_score(val_true_labels, val_predictions)
-    print(f'Validation Accuracy: {accuracy * 100:.2f}%')
-
-class DarkPatternDataset(Dataset):
-    def __init__(self, input_ids, attention_mask, labels):
-        self.input_ids = input_ids
-        self.attention_mask = attention_mask
-        self.labels = labels
-
-    def __len__(self):
-        return len(self.input_ids)
-
-    def __getitem__(self, idx):
-        return {'input_ids': self.input_ids[idx].squeeze(), 'attention_mask': self.attention_mask[idx].squeeze(), 'labels': self.labels[idx]}
diff --git a/api/mlApi/termsMlTrain.py b/api/mlApi/termsMlTrain.py
deleted file mode 100644
index 1e34223..0000000
--- a/api/mlApi/termsMlTrain.py
+++ /dev/null
@@ -1,41 +0,0 @@
-import torch
-from torch.utils.data import DataLoader, Dataset
-from transformers import BertTokenizer, BertForSequenceClassification, AdamW, get_linear_schedule_with_warmup
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score
-
-from termsMlModel import load_dataset, preprocess_data, train_model, evaluate_model
-
-# Task 1: Load your dataset
-dataset_path = 'path/to/your_dataset.csv'  # Replace with the path to your dataset
-texts, labels = load_dataset(dataset_path)
-
-# Task 2: Configure model parameters
-model_name = 'bert-base-uncased'
-num_labels = 2  # Binary classification (dark pattern or not)
-batch_size = 8
-max_length = 512  # Adjust based on your dataset and model's input size
-
-# Task 3: Preprocess the data
-# Split the dataset
-texts_train, texts_val, labels_train, labels_val = train_test_split(texts, labels, test_size=0.1, random_state=42)
-
-# Preprocess the training data
-train_dataset = preprocess_data(texts_train, labels_train, max_length)
-train_dataloader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
-
-# Preprocess the validation data
-val_dataset = preprocess_data(texts_val, labels_val, max_length)
-val_dataloader = DataLoader(val_dataset, batch_size=batch_size, shuffle=False)
-
-# Set up the BERT model
-model = BertForSequenceClassification.from_pretrained(model_name, num_labels=num_labels)
-
-# Train the model
-epochs = 3
-learning_rate = 2e-5
-train_model(model, train_dataloader, val_dataloader, epochs, learning_rate)
-
-# Evaluate the model
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-evaluate_model(model, val_dataloader, device)